Haploid-Diploid Evolutionary Algorithms
This work addresses a problem in evolutionary computation for researchers, but it appears incremental as it builds on existing ideas about haploid-diploid lifecycles.
The paper tackles the problem of improving evolutionary algorithms by deriving a general approach based on the haploid-diploid lifecycle, differing from prior diploid methods and changing the role of recombination. It shows that varying fitness landscape ruggedness affects the benefit of this new approach, using abstract tuneable models.
This paper uses the recent idea that the fundamental haploid-diploid lifecycle of eukaryotic organisms implements a rudimentary form of learning within evolution. A general approach for evolutionary computation is here derived that differs from all previous known work using diploid representations. The primary role of recombination is also changed from that previously considered in both natural and artificial evolution under the new view. Using well-known abstract tuneable models it is shown that varying fitness landscape ruggedness varies the benefit of the new approach.